## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.3     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

1 Initiating datasets

mpg
## # A tibble: 234 × 11
##    manufacturer model      displ  year   cyl trans drv     cty   hwy fl    class
##    <chr>        <chr>      <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
##  1 audi         a4           1.8  1999     4 auto… f        18    29 p     comp…
##  2 audi         a4           1.8  1999     4 manu… f        21    29 p     comp…
##  3 audi         a4           2    2008     4 manu… f        20    31 p     comp…
##  4 audi         a4           2    2008     4 auto… f        21    30 p     comp…
##  5 audi         a4           2.8  1999     6 auto… f        16    26 p     comp…
##  6 audi         a4           2.8  1999     6 manu… f        18    26 p     comp…
##  7 audi         a4           3.1  2008     6 auto… f        18    27 p     comp…
##  8 audi         a4 quattro   1.8  1999     4 manu… 4        18    26 p     comp…
##  9 audi         a4 quattro   1.8  1999     4 auto… 4        16    25 p     comp…
## 10 audi         a4 quattro   2    2008     4 manu… 4        20    28 p     comp…
## # … with 224 more rows

2 Basic information in plot

2.1 facets

display in small windows

  • group by single element and display randomly
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_wrap(~ class, nrow = 2)

  • group by double elements
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_grid(drv ~ cyl)

  • group by one element and display in rows or columns
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(drv ~ .)

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(. ~ cyl)

2.2 statistical transformation

line smooth

ggplot() + 
  geom_point(data = mpg, mapping = aes(x = displ, y = hwy)) + 
  geom_smooth(data = mpg, mapping = aes(x = displ, y = hwy))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

geom_bar or stat_count

demo <- tribble(
  ~cut,         ~freq,
  "Fair",       1610,
  "Good",       4906,
  "Very Good",  12082,
  "Premium",    13791,
  "Ideal",      21551
)

ggplot(data = demo) +
  geom_bar(mapping = aes(x = cut, y = freq), stat = "identity")

ggplot(data = diamonds) + 
  stat_count(mapping = aes(x = cut))

line-bar or stat_summary

ggplot(data = diamonds) + 
  stat_summary(
    mapping = aes(x = cut, y = depth),
    fun.min = min,
    fun.max = max,
    fun = median
  )

2.3 position adjustments

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = cut))

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity))

The stacking is performed automatically by the position adjustment specified by the position argument. If you don’t want a stacked bar chart, you can use one of three other options: “identity”, “dodge” or “fill”.

ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) + 
  geom_bar(alpha = 1/5, position = "identity")

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), position = "fill")

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")

2.4 Coordinate systems

90度翻转

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + 
  geom_boxplot()

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + 
  geom_boxplot() +
  coord_flip()

地图适应

nz <- map_data("nz")

ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black")

ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black") +
  coord_quickmap()

极坐标转换

bar <- ggplot(data = diamonds) + 
  geom_bar(
    mapping = aes(x = cut, fill = cut), 
    show.legend = FALSE,
    width = 1
  ) + 
  theme(aspect.ratio = 1) +
  labs(x = NULL, y = NULL)

bar + coord_flip()

bar + coord_polar()

3 Data transformations

3.1 Filter

comparison: R provides the standard suite: >, >=, <, <=, != (not equal), and == (equal).

library(nycflights13)
filter(flights, month == 1)
## # A tibble: 27,004 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # … with 26,994 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

logical operations: you’ll need to use Boolean operators yourself: & is “and”, | is “or”, and ! is “not”.

filter(flights, month == 11 | month == 12)
## # A tibble: 55,403 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013    11     1        5           2359         6      352            345
##  2  2013    11     1       35           2250       105      123           2356
##  3  2013    11     1      455            500        -5      641            651
##  4  2013    11     1      539            545        -6      856            827
##  5  2013    11     1      542            545        -3      831            855
##  6  2013    11     1      549            600       -11      912            923
##  7  2013    11     1      550            600       -10      705            659
##  8  2013    11     1      554            600        -6      659            701
##  9  2013    11     1      554            600        -6      826            827
## 10  2013    11     1      554            600        -6      749            751
## # … with 55,393 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

A useful short-hand for this problem is x %in% y. This will select every row where x is one of the values in y. We could use it to rewrite the code above:

filter(flights, month %in% c(11, 12))
## # A tibble: 55,403 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013    11     1        5           2359         6      352            345
##  2  2013    11     1       35           2250       105      123           2356
##  3  2013    11     1      455            500        -5      641            651
##  4  2013    11     1      539            545        -6      856            827
##  5  2013    11     1      542            545        -3      831            855
##  6  2013    11     1      549            600       -11      912            923
##  7  2013    11     1      550            600       -10      705            659
##  8  2013    11     1      554            600        -6      659            701
##  9  2013    11     1      554            600        -6      826            827
## 10  2013    11     1      554            600        -6      749            751
## # … with 55,393 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

If you want to determine if a value is missing, use is.na():

df <- tibble(x = c(1, NA, 3))
filter(df, is.na(x) | x > 1)
## # A tibble: 2 × 1
##       x
##   <dbl>
## 1    NA
## 2     3

3.2 Arrange

arrange(flights, year, month, day)
## # A tibble: 336,776 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

Use desc() to re-order by a column in descending order,Missing values are always sorted at the end.

arrange(flights, desc(dep_delay))
## # A tibble: 336,776 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     9      641            900      1301     1242           1530
##  2  2013     6    15     1432           1935      1137     1607           2120
##  3  2013     1    10     1121           1635      1126     1239           1810
##  4  2013     9    20     1139           1845      1014     1457           2210
##  5  2013     7    22      845           1600      1005     1044           1815
##  6  2013     4    10     1100           1900       960     1342           2211
##  7  2013     3    17     2321            810       911      135           1020
##  8  2013     6    27      959           1900       899     1236           2226
##  9  2013     7    22     2257            759       898      121           1026
## 10  2013    12     5      756           1700       896     1058           2020
## # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

3.3 Select

Select columns by name

select(flights, year, month, day)
## # A tibble: 336,776 × 3
##     year month   day
##    <int> <int> <int>
##  1  2013     1     1
##  2  2013     1     1
##  3  2013     1     1
##  4  2013     1     1
##  5  2013     1     1
##  6  2013     1     1
##  7  2013     1     1
##  8  2013     1     1
##  9  2013     1     1
## 10  2013     1     1
## # … with 336,766 more rows

Select all columns between year and day (inclusive)

select(flights, year:day)
## # A tibble: 336,776 × 3
##     year month   day
##    <int> <int> <int>
##  1  2013     1     1
##  2  2013     1     1
##  3  2013     1     1
##  4  2013     1     1
##  5  2013     1     1
##  6  2013     1     1
##  7  2013     1     1
##  8  2013     1     1
##  9  2013     1     1
## 10  2013     1     1
## # … with 336,766 more rows

Select all columns except those from year to day (inclusive)

select(flights, -(year:day))
## # A tibble: 336,776 × 16
##    dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier
##       <int>          <int>     <dbl>    <int>          <int>     <dbl> <chr>  
##  1      517            515         2      830            819        11 UA     
##  2      533            529         4      850            830        20 UA     
##  3      542            540         2      923            850        33 AA     
##  4      544            545        -1     1004           1022       -18 B6     
##  5      554            600        -6      812            837       -25 DL     
##  6      554            558        -4      740            728        12 UA     
##  7      555            600        -5      913            854        19 B6     
##  8      557            600        -3      709            723       -14 EV     
##  9      557            600        -3      838            846        -8 B6     
## 10      558            600        -2      753            745         8 AA     
## # … with 336,766 more rows, and 9 more variables: flight <int>, tailnum <chr>,
## #   origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## #   minute <dbl>, time_hour <dttm>

here are a number of helper functions you can use within select(): * starts_with(“abc”): matches names that begin with “abc”. * ends_with(“xyz”): matches names that end with “xyz”. * contains(“ijk”): matches names that contain “ijk”. * matches(“(.)\1”): selects variables that match a regular expression. This one matches any variables that contain repeated characters. * You’ll learn more about regular expressions in strings. * num_range(“x”, 1:3): matches x1, x2 and x3.

# rename columns 
rename(flights, tail_num = tailnum)
## # A tibble: 336,776 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      517            515         2      830            819
##  2  2013     1     1      533            529         4      850            830
##  3  2013     1     1      542            540         2      923            850
##  4  2013     1     1      544            545        -1     1004           1022
##  5  2013     1     1      554            600        -6      812            837
##  6  2013     1     1      554            558        -4      740            728
##  7  2013     1     1      555            600        -5      913            854
##  8  2013     1     1      557            600        -3      709            723
##  9  2013     1     1      557            600        -3      838            846
## 10  2013     1     1      558            600        -2      753            745
## # … with 336,766 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tail_num <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

3.4 Add

mutate() always adds new columns at the end of your dataset.

flights_sml <- select(flights, 
  year:day, 
  ends_with("delay"), 
  distance, 
  air_time
)
mutate(flights_sml,
  gain = dep_delay - arr_delay,
  speed = distance / air_time * 60
)
## # A tibble: 336,776 × 9
##     year month   day dep_delay arr_delay distance air_time  gain speed
##    <int> <int> <int>     <dbl>     <dbl>    <dbl>    <dbl> <dbl> <dbl>
##  1  2013     1     1         2        11     1400      227    -9  370.
##  2  2013     1     1         4        20     1416      227   -16  374.
##  3  2013     1     1         2        33     1089      160   -31  408.
##  4  2013     1     1        -1       -18     1576      183    17  517.
##  5  2013     1     1        -6       -25      762      116    19  394.
##  6  2013     1     1        -4        12      719      150   -16  288.
##  7  2013     1     1        -5        19     1065      158   -24  404.
##  8  2013     1     1        -3       -14      229       53    11  259.
##  9  2013     1     1        -3        -8      944      140     5  405.
## 10  2013     1     1        -2         8      733      138   -10  319.
## # … with 336,766 more rows

If you only want to keep the new variables, use transmute():

transmute(flights,
  gain = dep_delay - arr_delay,
  hours = air_time / 60,
  gain_per_hour = gain / hours
)
## # A tibble: 336,776 × 3
##     gain hours gain_per_hour
##    <dbl> <dbl>         <dbl>
##  1    -9 3.78          -2.38
##  2   -16 3.78          -4.23
##  3   -31 2.67         -11.6 
##  4    17 3.05           5.57
##  5    19 1.93           9.83
##  6   -16 2.5           -6.4 
##  7   -24 2.63          -9.11
##  8    11 0.883         12.5 
##  9     5 2.33           2.14
## 10   -10 2.3           -4.35
## # … with 336,766 more rows

  • useful operations

  • +, -, *, /, ^

  • “%/%” (integer division) and “%%” (remainder)

3.5 Group summarise

summarise(flights, delay = mean(dep_delay, na.rm = TRUE))
## # A tibble: 1 × 1
##   delay
##   <dbl>
## 1  12.6
delays <- flights %>% 
  group_by(dest) %>% 
  summarise(
    count = n(),
    dist = mean(distance, na.rm = TRUE),
    delay = mean(arr_delay, na.rm = TRUE)
  ) %>% 
  filter(count > 20, dest != "HNL")

ggplot(data = delays, mapping = aes(x = delay)) + 
  geom_freqpoly(binwidth = 10)

4 Scripts

4.1 parse vector

str(parse_logical(c("TRUE", "FALSE", "NA")))
##  logi [1:3] TRUE FALSE NA
#>  logi [1:3] TRUE FALSE NA
str(parse_integer(c("1", "2", "3")))
##  int [1:3] 1 2 3
#>  int [1:3] 1 2 3
str(parse_date(c("2010-01-01", "1979-10-14")))
##  Date[1:2], format: "2010-01-01" "1979-10-14"
#>  Date[1:2], format: "2010-01-01" "1979-10-14"
guess_parser("2010-10-01")
## [1] "date"
#> [1] "date"
guess_parser("15:01")
## [1] "time"
#> [1] "time"
guess_parser(c("TRUE", "FALSE"))
## [1] "logical"
#> [1] "logical"
guess_parser(c("1", "5", "9"))
## [1] "double"
#> [1] "double"
guess_parser(c("12,352,561"))
## [1] "number"
#> [1] "number"

str(parse_guess("2010-10-10"))
##  Date[1:1], format: "2010-10-10"
#>  Date[1:1], format: "2010-10-10"

4.2 pivot

  • longer

pivot the offending columns into a new pair of variables

table4a
## # A tibble: 3 × 3
##   country     `1999` `2000`
## * <chr>        <int>  <int>
## 1 Afghanistan    745   2666
## 2 Brazil       37737  80488
## 3 China       212258 213766
table4a %>% 
  pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")
## # A tibble: 6 × 3
##   country     year   cases
##   <chr>       <chr>  <int>
## 1 Afghanistan 1999     745
## 2 Afghanistan 2000    2666
## 3 Brazil      1999   37737
## 4 Brazil      2000   80488
## 5 China       1999  212258
## 6 China       2000  213766
  • wider

You use it when an observation is scattered across multiple rows

table2
## # A tibble: 12 × 4
##    country      year type            count
##    <chr>       <int> <chr>           <int>
##  1 Afghanistan  1999 cases             745
##  2 Afghanistan  1999 population   19987071
##  3 Afghanistan  2000 cases            2666
##  4 Afghanistan  2000 population   20595360
##  5 Brazil       1999 cases           37737
##  6 Brazil       1999 population  172006362
##  7 Brazil       2000 cases           80488
##  8 Brazil       2000 population  174504898
##  9 China        1999 cases          212258
## 10 China        1999 population 1272915272
## 11 China        2000 cases          213766
## 12 China        2000 population 1280428583
table2 %>%
    pivot_wider(names_from = type, values_from = count)
## # A tibble: 6 × 4
##   country      year  cases population
##   <chr>       <int>  <int>      <int>
## 1 Afghanistan  1999    745   19987071
## 2 Afghanistan  2000   2666   20595360
## 3 Brazil       1999  37737  172006362
## 4 Brazil       2000  80488  174504898
## 5 China        1999 212258 1272915272
## 6 China        2000 213766 1280428583
  • separate

separate() pulls apart one column into multiple columns, by splitting wherever a separator character appears

table3
## # A tibble: 6 × 3
##   country      year rate             
## * <chr>       <int> <chr>            
## 1 Afghanistan  1999 745/19987071     
## 2 Afghanistan  2000 2666/20595360    
## 3 Brazil       1999 37737/172006362  
## 4 Brazil       2000 80488/174504898  
## 5 China        1999 212258/1272915272
## 6 China        2000 213766/1280428583
table3 %>% 
  separate(rate, into = c("cases", "population"))
## # A tibble: 6 × 4
##   country      year cases  population
##   <chr>       <int> <chr>  <chr>     
## 1 Afghanistan  1999 745    19987071  
## 2 Afghanistan  2000 2666   20595360  
## 3 Brazil       1999 37737  172006362 
## 4 Brazil       2000 80488  174504898 
## 5 China        1999 212258 1272915272
## 6 China        2000 213766 1280428583
  • unite

unite() is the inverse of separate(): it combines multiple columns into a single column

table5
## # A tibble: 6 × 4
##   country     century year  rate             
## * <chr>       <chr>   <chr> <chr>            
## 1 Afghanistan 19      99    745/19987071     
## 2 Afghanistan 20      00    2666/20595360    
## 3 Brazil      19      99    37737/172006362  
## 4 Brazil      20      00    80488/174504898  
## 5 China       19      99    212258/1272915272
## 6 China       20      00    213766/1280428583
table5 %>% 
  unite(new, century, year)
## # A tibble: 6 × 3
##   country     new   rate             
##   <chr>       <chr> <chr>            
## 1 Afghanistan 19_99 745/19987071     
## 2 Afghanistan 20_00 2666/20595360    
## 3 Brazil      19_99 37737/172006362  
## 4 Brazil      20_00 80488/174504898  
## 5 China       19_99 212258/1272915272
## 6 China       20_00 213766/1280428583
  • join

inner_join 

x <- tribble(
  ~key, ~val_x,
     1, "x1",
     2, "x2",
     3, "x3"
)
y <- tribble(
  ~key, ~val_y,
     1, "y1",
     2, "y2",
     4, "y3"
)

x %>% 
  left_join(y, by = "key")
## # A tibble: 3 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA>
x %>% 
  right_join(y, by = "key")
## # A tibble: 3 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     4 <NA>  y3
x %>% 
  full_join(y, by = "key")
## # A tibble: 4 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     3 x3    <NA> 
## 4     4 <NA>  y3
  • duplicate keys

One table has duplicate keys. This is useful when you want to add in additional information as there is typically a one-to-many relationship.

duplicate

x <- tribble(
  ~key, ~val_x,
     1, "x1",
     2, "x2",
     2, "x3",
     1, "x4"
)
y <- tribble(
  ~key, ~val_y,
     1, "y1",
     2, "y2"
)
left_join(x, y, by = "key")
## # A tibble: 4 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     2 x3    y2   
## 4     1 x4    y1

duplicate

Both tables have duplicate keys. This is usually an error because in neither table do the keys uniquely identify an observation. When you join duplicated keys, you get all possible combinations, the Cartesian product:

x <- tribble(
  ~key, ~val_x,
     1, "x1",
     2, "x2",
     2, "x3",
     3, "x4"
)
y <- tribble(
  ~key, ~val_y,
     1, "y1",
     2, "y2",
     2, "y3",
     3, "y4"
)
left_join(x, y, by = "key")
## # A tibble: 6 × 3
##     key val_x val_y
##   <dbl> <chr> <chr>
## 1     1 x1    y1   
## 2     2 x2    y2   
## 3     2 x2    y3   
## 4     2 x3    y2   
## 5     2 x3    y3   
## 6     3 x4    y4
  • semi and anti

semi

top_dest <- flights %>%
  count(dest, sort = TRUE) %>%
  head(10)
flights %>% 
  semi_join(top_dest)
## Joining, by = "dest"
## # A tibble: 141,145 × 19
##     year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time
##    <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>
##  1  2013     1     1      542            540         2      923            850
##  2  2013     1     1      554            600        -6      812            837
##  3  2013     1     1      554            558        -4      740            728
##  4  2013     1     1      555            600        -5      913            854
##  5  2013     1     1      557            600        -3      838            846
##  6  2013     1     1      558            600        -2      753            745
##  7  2013     1     1      558            600        -2      924            917
##  8  2013     1     1      558            600        -2      923            937
##  9  2013     1     1      559            559         0      702            706
## 10  2013     1     1      600            600         0      851            858
## # … with 141,135 more rows, and 11 more variables: arr_delay <dbl>,
## #   carrier <chr>, flight <int>, tailnum <chr>, origin <chr>, dest <chr>,
## #   air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>, time_hour <dttm>

anti

flights %>%
  anti_join(planes, by = "tailnum") %>%
  count(tailnum, sort = TRUE)
## # A tibble: 722 × 2
##    tailnum     n
##    <chr>   <int>
##  1 <NA>     2512
##  2 N725MQ    575
##  3 N722MQ    513
##  4 N723MQ    507
##  5 N713MQ    483
##  6 N735MQ    396
##  7 N0EGMQ    371
##  8 N534MQ    364
##  9 N542MQ    363
## 10 N531MQ    349
## # … with 712 more rows

4.3 Strings

special character

x <- "\u00b5"

combination

str_c("x","y")
## [1] "xy"

subset

str_sub("i am a pretty girl", 3,12)
## [1] "am a prett"

You can pick which set of rules to use by specifying a locale:

str_to_upper(c("i", "ı"),locale = "tr")
## [1] "İ" "I"
x <- c("apple", "eggplant", "banana")

str_sort(x, locale = "en")  # English
## [1] "apple"    "banana"   "eggplant"
str_sort(x, locale = "haw") # Hawaiian
## [1] "apple"    "eggplant" "banana"

regular expressions

match

x <- c("apple", "banana", "pear")
str_view(x, "an")
str_view(x, ".a.")
str_view(c("abc", "a.c", "bef"), "a\\.c")

anchor

x <- c("apple", "banana", "pear")
## from start
str_view(x, "^a")
## to end
str_view(x, "a$")

Character classes and alternatives

  • matches any digit.
  • : matches any whitespace (e.g. space, tab, newline).
str_view(c("grey", "gray"), "gr(e|a)y")

Repetition

  • ?: 0 or 1
  • +: 1 or more
  • *: 0 or more
  • {n}: exactly n
  • {n,}: n or more
  • {,m}: at most m
  • {n,m}: between n and m

tools

detection

x <- c("apple", "banana", "pear")
str_detect(x, "e")
## [1]  TRUE FALSE  TRUE

extract

colours <- c("red", "orange", "yellow", "green", "blue", "purple")
colour_match <- str_c(colours, collapse = "|")
colour_match
## [1] "red|orange|yellow|green|blue|purple"
has_colour <- str_subset(sentences, colour_match)
matches <- str_extract(has_colour, colour_match)
head(matches)
## [1] "blue" "blue" "red"  "red"  "red"  "blue"

replace

x <- c("apple", "pear", "banana")
str_replace(x, "[aeiou]", "-")
## [1] "-pple"  "p-ar"   "b-nana"

splitting

sentences %>%
  head(5) %>% 
  str_split(" ")
## [[1]]
## [1] "The"     "birch"   "canoe"   "slid"    "on"      "the"     "smooth" 
## [8] "planks."
## 
## [[2]]
## [1] "Glue"        "the"         "sheet"       "to"          "the"        
## [6] "dark"        "blue"        "background."
## 
## [[3]]
## [1] "It's"  "easy"  "to"    "tell"  "the"   "depth" "of"    "a"     "well."
## 
## [[4]]
## [1] "These"   "days"    "a"       "chicken" "leg"     "is"      "a"      
## [8] "rare"    "dish."  
## 
## [[5]]
## [1] "Rice"   "is"     "often"  "served" "in"     "round"  "bowls."

4.4 Factors

ordering

library(ggplot2)
library(tidyverse)
gss_cat <- forcats::gss_cat

relig_summary <- gss_cat %>%
  group_by(relig) %>%
  summarise(
    age = mean(age, na.rm = TRUE),
    tvhours = mean(tvhours, na.rm = TRUE),
    n = n()
  )
#> `summarise()` ungrouping output (override with `.groups` argument)

# ggplot(relig_summary, aes(tvhours, relig)) + geom_point()

### fct_reorder 
# f, the factor whose levels you want to modify.
# x, a numeric vector that you want to use to reorder the levels.

ggplot(relig_summary, aes(tvhours, fct_reorder(relig, tvhours))) +
  geom_point()

### 使用 tidyverse + mutate 功能
relig_summary %>%
  mutate(relig = fct_reorder(relig, tvhours)) %>%
  ggplot(aes(tvhours, relig)) +
    geom_point()

### fct_level() It takes a factor, f, and then any number of levels that you want to move to the front of the line.
rincome_summary <- gss_cat %>%
  group_by(rincome) %>%
  summarise(
    age = mean(age, na.rm = TRUE),
    tvhours = mean(tvhours, na.rm = TRUE),
    n = n()
  )

ggplot(rincome_summary, aes(age, fct_relevel(rincome, "Not applicable"))) +
  geom_point()

### fct_reorder2() reorders the factor by the y values associated with the largest x values.
by_age <- gss_cat %>%
  filter(!is.na(age)) %>%
  count(age, marital) %>%
  group_by(age) %>%
  mutate(prop = n / sum(n))

ggplot(by_age, aes(age, prop, colour = marital)) +
  geom_line(na.rm = TRUE)

ggplot(by_age, aes(age, prop, colour = fct_reorder2(marital, age, prop))) +
  geom_line() +
  labs(colour = "marital")

### fct_infreq() order levels in increasing frequency
gss_cat %>%
  mutate(marital = marital %>% fct_infreq() %>% fct_rev()) %>%
  ggplot(aes(marital)) +
    geom_bar()

### If you want to collapse a lot of levels, fct_collapse()
gss_cat %>%
  mutate(partyid = fct_collapse(partyid,
    other = c("No answer", "Don't know", "Other party"),
    rep = c("Strong republican", "Not str republican"),
    ind = c("Ind,near rep", "Independent", "Ind,near dem"),
    dem = c("Not str democrat", "Strong democrat")
  )) %>%
  count(partyid)
## # A tibble: 4 × 2
##   partyid     n
##   <fct>   <int>
## 1 other     548
## 2 rep      5346
## 3 ind      8409
## 4 dem      7180
### Sometimes you just want to lump together all the small groups to make a plot or table simpler. That’s the job of fct_lump()
gss_cat %>%
  mutate(relig = fct_lump(relig)) %>%
  count(relig)
## # A tibble: 2 × 2
##   relig          n
##   <fct>      <int>
## 1 Protestant 10846
## 2 Other      10637

4.5 Dates and times

library(tidyverse)

library(lubridate)
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
library(nycflights13)

today()
## [1] "2021-10-25"
now()
## [1] "2021-10-25 22:11:45 CST"
ymd("2017-01-31")
## [1] "2017-01-31"
mdy("January 31st, 2017")
## [1] "2017-01-31"
dmy("31-Jan-2017")
## [1] "2017-01-31"
flights %>% 
  select(year, month, day, hour, minute)
## # A tibble: 336,776 × 5
##     year month   day  hour minute
##    <int> <int> <int> <dbl>  <dbl>
##  1  2013     1     1     5     15
##  2  2013     1     1     5     29
##  3  2013     1     1     5     40
##  4  2013     1     1     5     45
##  5  2013     1     1     6      0
##  6  2013     1     1     5     58
##  7  2013     1     1     6      0
##  8  2013     1     1     6      0
##  9  2013     1     1     6      0
## 10  2013     1     1     6      0
## # … with 336,766 more rows
flights %>% 
  select(year, month, day, hour, minute) %>% 
  mutate(departure = make_datetime(year, month, day, hour, minute))
## # A tibble: 336,776 × 6
##     year month   day  hour minute departure          
##    <int> <int> <int> <dbl>  <dbl> <dttm>             
##  1  2013     1     1     5     15 2013-01-01 05:15:00
##  2  2013     1     1     5     29 2013-01-01 05:29:00
##  3  2013     1     1     5     40 2013-01-01 05:40:00
##  4  2013     1     1     5     45 2013-01-01 05:45:00
##  5  2013     1     1     6      0 2013-01-01 06:00:00
##  6  2013     1     1     5     58 2013-01-01 05:58:00
##  7  2013     1     1     6      0 2013-01-01 06:00:00
##  8  2013     1     1     6      0 2013-01-01 06:00:00
##  9  2013     1     1     6      0 2013-01-01 06:00:00
## 10  2013     1     1     6      0 2013-01-01 06:00:00
## # … with 336,766 more rows
make_datetime_100 <- function(year, month, day, time) {
  make_datetime(year, month, day, time %/% 100, time %% 100)
}

flights_dt <- flights %>% 
  filter(!is.na(dep_time), !is.na(arr_time)) %>% 
  mutate(
    dep_time = make_datetime_100(year, month, day, dep_time),
    arr_time = make_datetime_100(year, month, day, arr_time),
    sched_dep_time = make_datetime_100(year, month, day, sched_dep_time),
    sched_arr_time = make_datetime_100(year, month, day, sched_arr_time)
  ) %>% 
  select(origin, dest, ends_with("delay"), ends_with("time"))


flights_dt %>% 
  filter(dep_time < ymd(20130102)) %>% 
  ggplot(aes(dep_time)) + 
  geom_freqpoly(binwidth = 600)

### get component
datetime <- ymd_hms("2021-10-25 20:34:56")

yday(datetime)
## [1] 298
wday(datetime)
## [1] 2
### Time span
# Durations
# periods
# intervals

# How old is Hadley?
h_age <- today() - ymd(19791014)
h_age
## Time difference of 15352 days
as.duration(h_age)
## [1] "1326412800s (~42.03 years)"
dseconds(15)
## [1] "15s"
dminutes(10)
## [1] "600s (~10 minutes)"
dhours(c(12, 24))
## [1] "43200s (~12 hours)" "86400s (~1 days)"
ddays(0:5)
## [1] "0s"                "86400s (~1 days)"  "172800s (~2 days)"
## [4] "259200s (~3 days)" "345600s (~4 days)" "432000s (~5 days)"
dweeks(3)
## [1] "1814400s (~3 weeks)"
dyears(1)
## [1] "31557600s (~1 years)"

5 Program

5.1 Pipes

library(magrittr)
## 
## Attaching package: 'magrittr'
## The following object is masked from 'package:purrr':
## 
##     set_names
## The following object is masked from 'package:tidyr':
## 
##     extract
diamonds <- ggplot2::diamonds
diamonds2 <- diamonds %>% 
  dplyr::mutate(price_per_carat = price / carat)

pryr::object_size(diamonds)
## 3,456,344 B
pryr::object_size(diamonds2)
## 3,887,976 B
pryr::object_size(diamonds, diamonds2)
## 3,888,552 B
## pryr::object_size() gives the memory occupied by all of its arguments. 

# Use function compose
# bop(
#   scoop(
#     hop(foo_foo, through = forest),
#     up = field_mice
#   ), 
#   on = head
# )

# Use pipes
# foo_foo %>%
#   hop(through = forest) %>%
#   scoop(up = field_mice) %>%
#   bop(on = head)

When not to use pipes ?

  • longer than (say) ten steps
  • multiple inputs or outputs

Other uses

# %T>% works like %>% except that it returns the left-hand side instead of the right-hand side
rnorm(100) %>%
  matrix(ncol = 2) %T>%
  plot() %>%
  str()

##  num [1:50, 1:2] 0.0895 -1.1249 -0.0675 -0.2693 0.4225 ...
# not a data frame and expressions to be evaluated in the context of that data frame), you might find %$% useful
mtcars %$%
  cor(disp, mpg)
## [1] -0.8475514
#  %<>% operator which allows you to replace code like:
mtcars <- mtcars %>% 
  transform(cyl = cyl * 2)

mtcars %<>% transform(cyl = cyl * 2)

5.2 Functions

df <- tibble::tibble(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)

df$a <- (df$a - min(df$a, na.rm = TRUE)) / 
  (max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))

rescale01 <- function(x) {
  rng <- range(x, na.rm = TRUE)
  (x - rng[1]) / (rng[2] - rng[1])
}

# arguments
mean_ci <- function(x, conf = 0.95) {
  se <- sd(x) / sqrt(length(x))
  alpha <- 1 - conf
  mean(x) + se * qnorm(c(alpha / 2, 1 - alpha / 2))
}

# ... captures any number of arguments that aren’t otherwise matched.
commas <- function(...) stringr::str_c(..., collapse = ", ")
commas(letters[1:10])
## [1] "a, b, c, d, e, f, g, h, i, j"

5.3 Vector

properties

typeof(letters)
## [1] "character"
length(letters[1:10])
## [1] 10

interrelationships

### Logical
1:10 %% 3 == 0
##  [1] FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE
### Numeric
typeof(1)
## [1] "double"
typeof(1L)
## [1] "integer"
### Character
x <- "This is a reasonably long string."
pryr::object_size(x)
## 152 B

  • coercion
    as.logical(), as.integer(), as.double(), or as.character()

  • check
    is_logical()
    is_integer() is_double() is_numeric() is_character() is_atomic() is_list()
    is_vector()

  • scalar and recycling
    tibble(x = 1:4, y = rep(1:2, each = 2))

  • naming
    set_names(1:3, c(“a”, “b”, “c”))

  • subsetting
    x <- c(“one”, “two”, “three”, “four”, “five”) x[c(3, 2, 5)]